NHV 2010
Erica
2023-01-16
Regression analysis
library(readxl)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(devtools)## Loading required package: usethislibrary(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2
## ──## ✔ ggplot2 3.4.0 ✔ purrr 1.0.1
## ✔ tibble 3.1.8 ✔ stringr 1.5.0
## ✔ tidyr 1.3.0 ✔ forcats 1.0.0
## ✔ readr 2.1.3
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()library(ggplot2)
library(GGally)## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2library(writexl)
df <- read_excel("data_2010.xlsx")z-score function
z_score <- function(x){
zscore=(x - mean(x, na.rm = TRUE))/sd(x, na.rm = TRUE)
zscore
}##Plotting ## Causality_log and Property Damage log
################### causality plot ################################
causality <- ggplot(df, aes(causality_log))
causality + geom_histogram(binwidth = 0.8) ### left-skewed 
################### Property Damage log ################################
property_damage_log<- ggplot(df, aes(prop_dmg_log))
property_damage_log + geom_histogram(binwidth = 1) 
CAUSALITY
Economic Dimension and Causality
### economic dimension VS causality log normalized plot
cor.test(df$causality_log, df$per_below_poverty_norm) # not statistically significant##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_below_poverty_norm
## t = -0.61014, df = 3120, p-value = 0.5418
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.04598514 0.02416692
## sample estimates:
## cor
## -0.01092255cor.test(df$causality_log, df$median_hh_income_2010_norm)# okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$median_hh_income_2010_norm
## t = 9.1914, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1280183 0.1963312
## sample estimates:
## cor
## 0.1623693cor.test(df$causality_log, df$per_rent_norm)# okay but removed do to correlation with no car##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_rent_norm
## t = 13.309, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1983111 0.2647068
## sample estimates:
## cor
## 0.2317789cor.test(df$causality_log, df$per_no_carnorm)#okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_no_carnorm
## t = -11.308, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2318929 -0.1644917
## sample estimates:
## cor
## -0.1984269cor.test(df$causality_log, df$per_college_or_higher_norm)# okay but removed due to correlation with hh income##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_college_or_higher_norm
## t = 13.436, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.2004345 0.2667620
## sample estimates:
## cor
## 0.2338703cor.test(df$causality_log, df$average_hh_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$average_hh_norm
## t = 7.7984, df = 3120, p-value = 8.479e-15
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1036959 0.1725166
## sample estimates:
## cor
## 0.1382732cor.test(df$causality_log, df$per_lack_plumbing_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_lack_plumbing_norm
## t = -2.2011, df = 3120, p-value = 0.0278
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.074353748 -0.004301982
## sample estimates:
## cor
## -0.03937625cor.test(df$causality_log, df$per_lack_kitchen_norm) #okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_lack_kitchen_norm
## t = -9.5853, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2030074 -0.1348516
## sample estimates:
## cor
## -0.1691317cor.test(df$causality_log, df$per_mobile_home_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_mobile_home_norm
## t = -4.2332, df = 3120, p-value = 2.37e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.11035818 -0.04059795
## sample estimates:
## cor
## -0.07557053cor.test(df$causality_log, df$per_unemployed_norm)## okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_unemployed_norm
## t = 8.7904, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1210399 0.1895068
## sample estimates:
## cor
## 0.15546X<-df%>%
select(
per_no_carnorm,
median_hh_income_2010_norm,
average_hh_norm,
per_lack_plumbing_norm,
per_lack_kitchen_norm,
per_mobile_home_norm,
per_unemployed_norm)
ggpairs(X)
econ_causality <- lm(causality_log~(
per_no_carnorm+median_hh_income_2010_norm+average_hh_norm+
per_lack_plumbing_norm+per_lack_kitchen_norm+
per_mobile_home_norm+per_unemployed_norm)+
log_pop_2010+numb_haz_log+state,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(econ_causality)##
## Call:
## lm(formula = causality_log ~ (per_no_carnorm + median_hh_income_2010_norm +
## average_hh_norm + per_lack_plumbing_norm + per_lack_kitchen_norm +
## per_mobile_home_norm + per_unemployed_norm) + log_pop_2010 +
## numb_haz_log + state, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5104 -0.6204 -0.1358 0.4699 5.0038
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -3.3861588 0.3223726 -10.504 < 2e-16 ***
## per_no_carnorm -0.0414919 0.0215498 -1.925 0.05427 .
## median_hh_income_2010_norm 0.0730351 0.0287588 2.540 0.01115 *
## average_hh_norm -0.1212188 0.0242137 -5.006 5.87e-07 ***
## per_lack_plumbing_norm -0.0248460 0.0268350 -0.926 0.35458
## per_lack_kitchen_norm 0.0678691 0.0256898 2.642 0.00829 **
## per_mobile_home_norm 0.0229197 0.0269185 0.851 0.39459
## per_unemployed_norm 0.0618163 0.0252373 2.449 0.01437 *
## log_pop_2010 0.3760709 0.0199066 18.892 < 2e-16 ***
## numb_haz_log 0.4554903 0.0404987 11.247 < 2e-16 ***
## stateAL 0.6882991 0.3055490 2.253 0.02435 *
## stateAR 0.0212880 0.3009603 0.071 0.94361
## stateAZ 0.5132597 0.3651433 1.406 0.15993
## stateCA 0.1891042 0.3000959 0.630 0.52865
## stateCO 0.1282804 0.2979590 0.431 0.66684
## stateCT -0.6358297 0.4333707 -1.467 0.14243
## stateDE 0.4233034 0.6151623 0.688 0.49143
## stateFL -0.1422031 0.3095652 -0.459 0.64601
## stateGA -0.3119362 0.2918722 -1.069 0.28527
## stateIA -0.5053658 0.2973231 -1.700 0.08929 .
## stateID -0.3231649 0.3137847 -1.030 0.30314
## stateIL -0.1346395 0.2950242 -0.456 0.64816
## stateIN -0.3930954 0.2969107 -1.324 0.18562
## stateKS -0.0572892 0.2940989 -0.195 0.84557
## stateKY -0.1482506 0.2923074 -0.507 0.61207
## stateLA -0.1975775 0.3037323 -0.650 0.51542
## stateMA -0.5580614 0.3747204 -1.489 0.13652
## stateMD -0.5270512 0.3354717 -1.571 0.11627
## stateME -0.8955222 0.3651165 -2.453 0.01423 *
## stateMI -0.7783866 0.3031774 -2.567 0.01029 *
## stateMN -0.5980852 0.2971311 -2.013 0.04422 *
## stateMO 0.1646739 0.2928636 0.562 0.57396
## stateMS 0.2467886 0.3019792 0.817 0.41386
## stateMT 0.1009132 0.3014277 0.335 0.73781
## stateNC -0.2388775 0.2991553 -0.799 0.42464
## stateND -0.1936113 0.3097492 -0.625 0.53198
## stateNE -0.1023200 0.2967725 -0.345 0.73029
## stateNH 0.0003921 0.4069369 0.001 0.99923
## stateNJ 0.5450307 0.3435431 1.586 0.11273
## stateNM -0.0080808 0.3188830 -0.025 0.97978
## stateNV 0.0907099 0.3592581 0.252 0.80068
## stateNY -0.6102058 0.3042849 -2.005 0.04501 *
## stateOH -0.8383211 0.2973947 -2.819 0.00485 **
## stateOK 0.3722527 0.2992051 1.244 0.21354
## stateOR -0.3649208 0.3187720 -1.145 0.25239
## statePA -0.6551946 0.3037124 -2.157 0.03106 *
## stateRI -1.3993684 0.5479918 -2.554 0.01071 *
## stateSC -0.3550726 0.3168513 -1.121 0.26253
## stateSD 0.0439281 0.3014806 0.146 0.88416
## stateTN -0.2187329 0.2977910 -0.735 0.46269
## stateTX -0.0721471 0.2818921 -0.256 0.79802
## stateUT 0.6441839 0.3343267 1.927 0.05410 .
## stateVA -0.4781443 0.2857243 -1.673 0.09434 .
## stateVT -0.6655584 0.3750534 -1.775 0.07607 .
## stateWA -0.3921607 0.3168305 -1.238 0.21590
## stateWI -0.4444524 0.2991139 -1.486 0.13741
## stateWV -0.6199811 0.3097681 -2.001 0.04543 *
## stateWY 0.1747456 0.3370993 0.518 0.60423
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9473 on 3064 degrees of freedom
## Multiple R-squared: 0.3595, Adjusted R-squared: 0.3476
## F-statistic: 30.18 on 57 and 3064 DF, p-value: < 2.2e-16Health Dimension and Causality
cor.test(df$causality_log, df$life_expectancy_2010_norm) # okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$life_expectancy_2010_norm
## t = -2.9141, df = 3120, p-value = 0.003593
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.08702054 -0.01705033
## sample estimates:
## cor
## -0.05209937cor.test(df$causality_log, df$per_hypertension_2009_norm)# no##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_hypertension_2009_norm
## t = -0.39005, df = 3120, p-value = 0.6965
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.04205268 0.02810432
## sample estimates:
## cor
## -0.006982771cor.test(df$causality_log, df$per_diabetes_2010_norm)#okay removed due to high correlation##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_diabetes_2010_norm
## t = 2.6552, df = 3120, p-value = 0.007968
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.01242173 0.08242417
## sample estimates:
## cor
## 0.04748125cor.test(df$causality_log, df$per_disability_norm)# okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_disability_norm
## t = 0.98026, df = 3120, p-value = 0.327
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.01754416 0.05259468
## sample estimates:
## cor
## 0.01754685cor.test(df$causality_log, df$per_nursingnorm)# okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_nursingnorm
## t = -9.888, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2081217 -0.1400906
## sample estimates:
## cor
## -0.1743142#cor.test(df$causality_norm_log, df$per_institutionalized_norm)## OKAY
X<-df%>%
select(life_expectancy_2010_norm,
per_disability_norm,
per_nursingnorm)
ggpairs(X)
health_causality <- lm(causality_log~(life_expectancy_2010_norm+
per_disability_norm+
per_nursingnorm)+
log_pop_2010+numb_haz_norm+state,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(health_causality)##
## Call:
## lm(formula = causality_log ~ (life_expectancy_2010_norm + per_disability_norm +
## per_nursingnorm) + log_pop_2010 + numb_haz_norm + state,
## data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.3647 -0.6309 -0.1352 0.4613 4.8914
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2.273941 0.259287 -8.770 < 2e-16 ***
## life_expectancy_2010_norm -0.038090 0.025191 -1.512 0.130625
## per_disability_norm 0.024030 0.018281 1.314 0.188777
## per_nursingnorm 0.001919 0.019555 0.098 0.921821
## log_pop_2010 0.349885 0.016035 21.821 < 2e-16 ***
## numb_haz_norm 0.261261 0.020596 12.685 < 2e-16 ***
## stateAL 0.559947 0.245636 2.280 0.022701 *
## stateAR -0.166654 0.242791 -0.686 0.492507
## stateAZ 0.305168 0.326299 0.935 0.349738
## stateCA 0.066472 0.250537 0.265 0.790783
## stateCO 0.117842 0.245331 0.480 0.631021
## stateCT -0.600854 0.400839 -1.499 0.133979
## stateDE 0.306798 0.588570 0.521 0.602223
## stateFL -0.254054 0.244619 -1.039 0.299086
## stateGA -0.507924 0.227047 -2.237 0.025352 *
## stateIA -0.706420 0.238273 -2.965 0.003053 **
## stateID -0.566300 0.257241 -2.201 0.027779 *
## stateIL -0.268606 0.234525 -1.145 0.252166
## stateIN -0.523513 0.236542 -2.213 0.026957 *
## stateKS -0.233095 0.234243 -0.995 0.319767
## stateKY -0.306151 0.231794 -1.321 0.186670
## stateLA -0.431032 0.246142 -1.751 0.080020 .
## stateMA -0.580208 0.335755 -1.728 0.084076 .
## stateMD -0.586431 0.290182 -2.021 0.043377 *
## stateME -0.903596 0.320254 -2.822 0.004811 **
## stateMI -0.807118 0.238392 -3.386 0.000719 ***
## stateMN -0.699219 0.239880 -2.915 0.003584 **
## stateMO -0.042182 0.232447 -0.181 0.856010
## stateMS -0.052603 0.241297 -0.218 0.827444
## stateMT -0.118549 0.247883 -0.478 0.632510
## stateNC -0.339926 0.235151 -1.446 0.148401
## stateND -0.267373 0.252024 -1.061 0.288818
## stateNE -0.299130 0.238567 -1.254 0.209988
## stateNH 0.042618 0.369792 0.115 0.908256
## stateNJ 0.428098 0.302377 1.416 0.156942
## stateNM -0.121712 0.269542 -0.452 0.651624
## stateNV 0.053860 0.312719 0.172 0.863267
## stateNY -0.650342 0.248134 -2.621 0.008812 **
## stateOH -0.933847 0.238912 -3.909 9.48e-05 ***
## stateOK 0.195884 0.240305 0.815 0.415050
## stateOR -0.415522 0.265983 -1.562 0.118341
## statePA -0.695500 0.244983 -2.839 0.004556 **
## stateRI -1.382003 0.521445 -2.650 0.008083 **
## stateSC -0.483216 0.257156 -1.879 0.060329 .
## stateSD -0.131633 0.243891 -0.540 0.589429
## stateTN -0.366095 0.236791 -1.546 0.122191
## stateTX -0.318384 0.222213 -1.433 0.152020
## stateUT 0.237381 0.277269 0.856 0.391987
## stateVA -0.546742 0.228714 -2.391 0.016885 *
## stateVT -0.736890 0.332195 -2.218 0.026611 *
## stateWA -0.468405 0.264549 -1.771 0.076730 .
## stateWI -0.504570 0.243075 -2.076 0.037998 *
## stateWV -0.779520 0.250209 -3.115 0.001853 **
## stateWY 0.045603 0.290648 0.157 0.875333
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9465 on 3068 degrees of freedom
## Multiple R-squared: 0.3598, Adjusted R-squared: 0.3488
## F-statistic: 32.53 on 53 and 3068 DF, p-value: < 2.2e-16Institutional Dimension and Causality
cor.test(df$causality_log, df$FEMA_total_norm) # okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$FEMA_total_norm
## t = 6.0706, df = 3120, p-value = 1.428e-09
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.0732424 0.1425848
## sample estimates:
## cor
## 0.108045cor.test(df$causality_log, df$number_research_institutions_norm) # okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$number_research_institutions_norm
## t = 15.677, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.2373922 0.3024354
## sample estimates:
## cor
## 0.2702221cor.test(df$causality_log, df$employees_2010_norm) # okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$employees_2010_norm
## t = 21.638, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.3303357 0.3913509
## sample estimates:
## cor
## 0.3612299X<-df%>%
select(
FEMA_total_norm,
number_research_institutions_norm,
employees_2010_norm)
ggpairs(X)
inst_causality <- lm(causality_log~(FEMA_total_norm+
number_research_institutions_norm+
employees_2010_norm)+
log_pop_2010+numb_haz_log+state,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(inst_causality)##
## Call:
## lm(formula = causality_log ~ (FEMA_total_norm + number_research_institutions_norm +
## employees_2010_norm) + log_pop_2010 + numb_haz_log + state,
## data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.2923 -0.6292 -0.1483 0.4561 5.1304
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2.413155 0.258468 -9.336 < 2e-16 ***
## FEMA_total_norm -0.009134 0.018773 -0.487 0.626609
## number_research_institutions_norm 0.051785 0.023050 2.247 0.024734 *
## employees_2010_norm 0.126506 0.025114 5.037 5.00e-07 ***
## log_pop_2010 0.295237 0.017018 17.349 < 2e-16 ***
## numb_haz_log 0.462217 0.040125 11.520 < 2e-16 ***
## stateAL 0.605300 0.241935 2.502 0.012404 *
## stateAR -0.087236 0.239698 -0.364 0.715927
## stateAZ 0.280609 0.325378 0.862 0.388529
## stateCA -0.061911 0.249777 -0.248 0.804256
## stateCO 0.024544 0.242574 0.101 0.919414
## stateCT -0.676806 0.398199 -1.700 0.089295 .
## stateDE 0.333477 0.586651 0.568 0.569776
## stateFL -0.231205 0.244182 -0.947 0.343786
## stateGA -0.481916 0.225615 -2.136 0.032757 *
## stateIA -0.686545 0.233600 -2.939 0.003318 **
## stateID -0.601001 0.255214 -2.355 0.018591 *
## stateIL -0.283184 0.232133 -1.220 0.222588
## stateIN -0.535519 0.234158 -2.287 0.022264 *
## stateKS -0.262757 0.230429 -1.140 0.254252
## stateKY -0.297409 0.229045 -1.298 0.194221
## stateLA -0.345987 0.244836 -1.413 0.157717
## stateMA -0.660796 0.333731 -1.980 0.047790 *
## stateMD -0.615009 0.288640 -2.131 0.033192 *
## stateME -0.892986 0.318010 -2.808 0.005016 **
## stateMI -0.844667 0.236928 -3.565 0.000369 ***
## stateMN -0.761225 0.235012 -3.239 0.001212 **
## stateMO 0.004474 0.229181 0.020 0.984427
## stateMS 0.072118 0.237784 0.303 0.761687
## stateMT -0.030619 0.245997 -0.124 0.900951
## stateNC -0.299207 0.233600 -1.281 0.200341
## stateND -0.408611 0.248723 -1.643 0.100519
## stateNE -0.338471 0.233213 -1.451 0.146788
## stateNH -0.034395 0.367275 -0.094 0.925394
## stateNJ 0.435199 0.299845 1.451 0.146767
## stateNM -0.128745 0.268899 -0.479 0.632127
## stateNV 0.003621 0.311811 0.012 0.990736
## stateNY -0.771887 0.246297 -3.134 0.001741 **
## stateOH -0.951045 0.235977 -4.030 5.71e-05 ***
## stateOK 0.206715 0.238162 0.868 0.385485
## stateOR -0.415780 0.264112 -1.574 0.115531
## statePA -0.727558 0.243132 -2.992 0.002790 **
## stateRI -1.437767 0.519450 -2.768 0.005676 **
## stateSC -0.405608 0.255468 -1.588 0.112457
## stateSD -0.185151 0.241438 -0.767 0.443221
## stateTN -0.338001 0.233689 -1.446 0.148176
## stateTX -0.305937 0.220403 -1.388 0.165213
## stateUT 0.191574 0.275798 0.695 0.487349
## stateVA -0.577794 0.227478 -2.540 0.011134 *
## stateVT -0.726516 0.330428 -2.199 0.027973 *
## stateWA -0.499204 0.262510 -1.902 0.057309 .
## stateWI -0.540814 0.240376 -2.250 0.024528 *
## stateWV -0.752151 0.247578 -3.038 0.002401 **
## stateWY 0.078836 0.288802 0.273 0.784891
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9437 on 3068 degrees of freedom
## Multiple R-squared: 0.3637, Adjusted R-squared: 0.3527
## F-statistic: 33.08 on 53 and 3068 DF, p-value: < 2.2e-16Environmental Dimension and Causality
df$air_quality_norm <- z_score(df$air_quality)
df$water_quality_norm <- z_score(df$water_quality)
df$built_quality_norm <- z_score(df$built_quality)
df$land_quality_norm <- z_score(df$land_quality)
cor.test(df$causality_log, df$air_quality_norm)# okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$air_quality_norm
## t = 4.0565, df = 3120, p-value = 5.104e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.03744641 0.10723919
## sample estimates:
## cor
## 0.07243147cor.test(df$causality_log, df$water_quality_norm)# no##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$water_quality_norm
## t = 2.2666, df = 3120, p-value = 0.02348
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.005473475 0.075518691
## sample estimates:
## cor
## 0.0405459cor.test(df$causality_log, df$built_quality_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$built_quality_norm
## t = 5.8142, df = 3120, p-value = 6.709e-09
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.06870033 0.13810964
## sample estimates:
## cor
## 0.103531cor.test(df$causality_log, df$land_quality_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$land_quality_norm
## t = -4.4465, df = 3120, p-value = 9.032e-06
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1141170 -0.0443979
## sample estimates:
## cor
## -0.07935451cor.test(df$causality_log, df$impervious_surface_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$impervious_surface_norm
## t = 17.611, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.268441 0.332265
## sample estimates:
## cor
## 0.3006896X<-df%>%
select(
air_quality_norm,
built_quality_norm,
land_quality_norm,
impervious_surface_norm)
ggpairs(X)
environ_causality <- lm(causality_log~(air_quality_norm+
built_quality_norm+
land_quality_norm+
impervious_surface_norm)+
log_pop_2010+numb_haz_log+state,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(environ_causality)##
## Call:
## lm(formula = causality_log ~ (air_quality_norm + built_quality_norm +
## land_quality_norm + impervious_surface_norm) + log_pop_2010 +
## numb_haz_log + state, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5264 -0.6262 -0.1492 0.4730 5.0667
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -3.128805 0.305801 -10.232 < 2e-16 ***
## air_quality_norm 0.004587 0.025763 0.178 0.858698
## built_quality_norm -0.042356 0.021495 -1.970 0.048873 *
## land_quality_norm -0.087124 0.023585 -3.694 0.000225 ***
## impervious_surface_norm 0.093890 0.023766 3.951 7.97e-05 ***
## log_pop_2010 0.333164 0.018294 18.212 < 2e-16 ***
## numb_haz_log 0.469179 0.040251 11.656 < 2e-16 ***
## stateAL 0.936788 0.264838 3.537 0.000410 ***
## stateAR 0.243191 0.261747 0.929 0.352907
## stateAZ 0.636297 0.332901 1.911 0.056050 .
## stateCA 0.376624 0.266540 1.413 0.157754
## stateCO 0.286186 0.255582 1.120 0.262911
## stateCT -0.396541 0.413278 -0.960 0.337382
## stateDE 0.658968 0.601649 1.095 0.273485
## stateFL 0.057575 0.261884 0.220 0.826005
## stateGA -0.160508 0.250695 -0.640 0.522056
## stateIA -0.310997 0.264619 -1.175 0.239981
## stateID -0.296389 0.271777 -1.091 0.275553
## stateIL 0.093991 0.264678 0.355 0.722527
## stateIN -0.180911 0.268102 -0.675 0.499862
## stateKS 0.104826 0.257232 0.408 0.683658
## stateKY 0.023918 0.254639 0.094 0.925171
## stateLA -0.054066 0.267946 -0.202 0.840103
## stateMA -0.447070 0.353724 -1.264 0.206364
## stateMD -0.317943 0.315546 -1.008 0.313728
## stateME -0.676611 0.329226 -2.055 0.039948 *
## stateMI -0.561405 0.261128 -2.150 0.031640 *
## stateMN -0.413242 0.261537 -1.580 0.114198
## stateMO 0.338801 0.252896 1.340 0.180446
## stateMS 0.417459 0.262683 1.589 0.112115
## stateMT 0.278343 0.260041 1.070 0.284533
## stateNC 0.015290 0.258663 0.059 0.952867
## stateND -0.006382 0.273938 -0.023 0.981414
## stateNE 0.048536 0.259849 0.187 0.851841
## stateNH 0.194271 0.377690 0.514 0.607033
## stateNJ 0.588955 0.330241 1.783 0.074619 .
## stateNM 0.099308 0.276148 0.360 0.719157
## stateNV 0.239457 0.316979 0.755 0.450046
## stateNY -0.442532 0.273494 -1.618 0.105751
## stateOH -0.619602 0.270262 -2.293 0.021939 *
## stateOK 0.539239 0.258324 2.087 0.036930 *
## stateOR -0.157977 0.281634 -0.561 0.574886
## statePA -0.443243 0.269789 -1.643 0.100501
## stateRI -1.310872 0.536768 -2.442 0.014656 *
## stateSC -0.095884 0.277542 -0.345 0.729760
## stateSD 0.196381 0.264479 0.743 0.457829
## stateTN -0.019577 0.258912 -0.076 0.939732
## stateTX 0.031128 0.242073 0.129 0.897690
## stateUT 0.447044 0.285033 1.568 0.116892
## stateVA -0.454541 0.252694 -1.799 0.072151 .
## stateVT -0.463695 0.342936 -1.352 0.176433
## stateWA -0.201018 0.278885 -0.721 0.471094
## stateWI -0.217369 0.266290 -0.816 0.414399
## stateWV -0.475318 0.270217 -1.759 0.078673 .
## stateWY 0.307465 0.298040 1.032 0.302331
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9436 on 3067 degrees of freedom
## Multiple R-squared: 0.3639, Adjusted R-squared: 0.3527
## F-statistic: 32.49 on 54 and 3067 DF, p-value: < 2.2e-16Aggregated Casualties
X<-df%>%
select(
per_black_norm,
per_hispanic_norm,
per_asian_norm,
per_elderly_norm,
per_young_dependent_norm,
per_foreign_born_norm,
per_female_hh_with_kids_under6_norm,
per_rural_norm,
per_no_carnorm,
median_hh_income_2010_norm,
average_hh_norm,
per_lack_plumbing_norm,
per_lack_kitchen_norm,
per_mobile_home_norm,
per_unemployed_norm,
life_expectancy_2010_norm,
per_disability_norm,
per_nursingnorm,
FEMA_total_norm,
number_research_institutions_norm,
employees_2010_norm,
air_quality_norm,
built_quality_norm,
land_quality_norm,
impervious_surface_norm
)
ggpairs(X)
aggregated_causality <- lm(causality_log~(per_black_norm+
per_hispanic_norm+
per_asian_norm+
per_elderly_norm+
per_young_dependent_norm+
per_foreign_born_norm+
per_female_hh_with_kids_under6_norm+
per_rural_norm+
per_no_carnorm+
median_hh_income_2010_norm+
per_lack_plumbing_norm+
per_lack_kitchen_norm+
per_mobile_home_norm+
per_unemployed_norm+
life_expectancy_2010_norm+
per_disability_norm+
per_nursingnorm+
FEMA_total_norm+
number_research_institutions_norm+
employees_2010_norm+
air_quality_norm+
built_quality_norm+
land_quality_norm+
impervious_surface_norm)+
log_pop_2010+numb_haz_log+state,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(aggregated_causality)##
## Call:
## lm(formula = causality_log ~ (per_black_norm + per_hispanic_norm +
## per_asian_norm + per_elderly_norm + per_young_dependent_norm +
## per_foreign_born_norm + per_female_hh_with_kids_under6_norm +
## per_rural_norm + per_no_carnorm + median_hh_income_2010_norm +
## per_lack_plumbing_norm + per_lack_kitchen_norm + per_mobile_home_norm +
## per_unemployed_norm + life_expectancy_2010_norm + per_disability_norm +
## per_nursingnorm + FEMA_total_norm + number_research_institutions_norm +
## employees_2010_norm + air_quality_norm + built_quality_norm +
## land_quality_norm + impervious_surface_norm) + log_pop_2010 +
## numb_haz_log + state, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.5528 -0.6106 -0.1366 0.4578 5.1003
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -3.0625214 0.4154828 -7.371 2.17e-13 ***
## per_black_norm 0.0004696 0.0311553 0.015 0.987976
## per_hispanic_norm -0.0983309 0.0565091 -1.740 0.081945 .
## per_asian_norm -0.0995777 0.0373593 -2.665 0.007730 **
## per_elderly_norm 0.0950344 0.0345889 2.748 0.006040 **
## per_young_dependent_norm 0.0314660 0.0261130 1.205 0.228299
## per_foreign_born_norm 0.0439300 0.0399240 1.100 0.271270
## per_female_hh_with_kids_under6_norm -0.1028686 0.0336469 -3.057 0.002253 **
## per_rural_norm 0.0506493 0.0377458 1.342 0.179744
## per_no_carnorm -0.0965842 0.0273829 -3.527 0.000426 ***
## median_hh_income_2010_norm 0.0929921 0.0391388 2.376 0.017565 *
## per_lack_plumbing_norm -0.0382499 0.0266424 -1.436 0.151197
## per_lack_kitchen_norm 0.0214347 0.0265471 0.807 0.419485
## per_mobile_home_norm 0.0131740 0.0301217 0.437 0.661882
## per_unemployed_norm 0.0364521 0.0261123 1.396 0.162824
## life_expectancy_2010_norm -0.1137670 0.0368796 -3.085 0.002055 **
## per_disability_norm 0.0207253 0.0182323 1.137 0.255738
## per_nursingnorm -0.0410858 0.0216995 -1.893 0.058400 .
## FEMA_total_norm -0.0144776 0.0187611 -0.772 0.440363
## number_research_institutions_norm 0.0454613 0.0239859 1.895 0.058143 .
## employees_2010_norm 0.0965624 0.0270217 3.574 0.000358 ***
## air_quality_norm 0.0093550 0.0255679 0.366 0.714473
## built_quality_norm -0.0467454 0.0263271 -1.776 0.075905 .
## land_quality_norm -0.0754805 0.0249947 -3.020 0.002550 **
## impervious_surface_norm 0.0688846 0.0280675 2.454 0.014174 *
## log_pop_2010 0.3560696 0.0287141 12.400 < 2e-16 ***
## numb_haz_log 0.4510114 0.0403054 11.190 < 2e-16 ***
## stateAL 0.5441721 0.3400826 1.600 0.109676
## stateAR -0.1014560 0.3304953 -0.307 0.758878
## stateAZ 0.2241483 0.3861092 0.581 0.561600
## stateCA -0.0359253 0.3248043 -0.111 0.911936
## stateCO 0.0709653 0.3200670 0.222 0.824547
## stateCT -0.7712391 0.4535581 -1.700 0.089154 .
## stateDE 0.3281609 0.6293719 0.521 0.602119
## stateFL -0.3385487 0.3397182 -0.997 0.319059
## stateGA -0.4749372 0.3263562 -1.455 0.145697
## stateIA -0.4894617 0.3297612 -1.484 0.137835
## stateID -0.5746052 0.3364834 -1.708 0.087798 .
## stateIL -0.1675275 0.3313880 -0.506 0.613221
## stateIN -0.4669845 0.3347149 -1.395 0.163066
## stateKS -0.1664458 0.3226202 -0.516 0.605949
## stateKY -0.3119655 0.3243034 -0.962 0.336148
## stateLA -0.3194780 0.3382321 -0.945 0.344962
## stateMA -0.7937193 0.4023040 -1.973 0.048593 *
## stateMD -0.6687714 0.3693692 -1.811 0.070305 .
## stateME -0.9257410 0.3815376 -2.426 0.015310 *
## stateMI -0.8263552 0.3319314 -2.490 0.012844 *
## stateMN -0.5281740 0.3260035 -1.620 0.105304
## stateMO 0.0196158 0.3226684 0.061 0.951529
## stateMS 0.0746482 0.3393083 0.220 0.825885
## stateMT -0.0641846 0.3236026 -0.198 0.842789
## stateNC -0.3327600 0.3332557 -0.999 0.318110
## stateND -0.3008809 0.3383800 -0.889 0.373976
## stateNE -0.2259633 0.3284260 -0.688 0.491493
## stateNH -0.1070901 0.4230112 -0.253 0.800161
## stateNJ 0.2638799 0.3788736 0.696 0.486178
## stateNM 0.0588487 0.3484481 0.169 0.865896
## stateNV -0.2145717 0.3732028 -0.575 0.565370
## stateNY -0.7402062 0.3371469 -2.196 0.028203 *
## stateOH -0.9086967 0.3380668 -2.688 0.007229 **
## stateOK 0.1454400 0.3259183 0.446 0.655451
## stateOR -0.5330327 0.3441471 -1.549 0.121521
## statePA -0.7484568 0.3383862 -2.212 0.027052 *
## stateRI -1.6210832 0.5720037 -2.834 0.004627 **
## stateSC -0.4413443 0.3512313 -1.257 0.209008
## stateSD -0.1062191 0.3278206 -0.324 0.745948
## stateTN -0.4190310 0.3314591 -1.264 0.206254
## stateTX -0.2226069 0.3165023 -0.703 0.481901
## stateUT 0.1319714 0.3507282 0.376 0.706736
## stateVA -0.7234541 0.3242803 -2.231 0.025757 *
## stateVT -0.6771925 0.3917275 -1.729 0.083958 .
## stateWA -0.4886484 0.3390219 -1.441 0.149589
## stateWI -0.4414980 0.3309294 -1.334 0.182266
## stateWV -0.7668092 0.3407214 -2.251 0.024485 *
## stateWY 0.0094247 0.3540759 0.027 0.978766
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9325 on 3047 degrees of freedom
## Multiple R-squared: 0.3829, Adjusted R-squared: 0.3679
## F-statistic: 25.55 on 74 and 3047 DF, p-value: < 2.2e-16PROPERTY DAMAGE
Social Dimension and Prop Damage
### social dimension VS property dmg
cor.test(df$prop_dmg_log, df$per_white_norm) ## okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_white_norm
## t = -7.5933, df = 3120, p-value = 4.094e-14
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1689850 -0.1000961
## sample estimates:
## cor
## -0.1347033cor.test(df$prop_dmg_log, df$per_black_norm)# okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_black_norm
## t = 9.3579, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1309090 0.1991563
## sample estimates:
## cor
## 0.1652305cor.test(df$prop_dmg_log, df$per_hispanic_norm)##not statistically signif##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_hispanic_norm
## t = 1.709, df = 3120, p-value = 0.08754
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.004502708 0.065592169
## sample estimates:
## cor
## 0.03058233cor.test(df$prop_dmg_log, df$per_asian_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_asian_norm
## t = 7.5287, df = 3120, p-value = 6.667e-14
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.09896134 0.16787139
## sample estimates:
## cor
## 0.1335778cor.test(df$prop_dmg_log, df$per_american_indian_norm)# okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_american_indian_norm
## t = -5.8868, df = 3120, p-value = 4.357e-09
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.13937711 -0.06998647
## sample estimates:
## cor
## -0.1048094cor.test(df$prop_dmg_log, df$per_other_races_norm)#okay remove due to correlation##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_other_races_norm
## t = 3.7727, df = 3120, p-value = 0.0001645
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.03238429 0.10222649
## sample estimates:
## cor
## 0.06738794cor.test(df$prop_dmg_log, df$per_POC_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_POC_norm
## t = 6.4655, df = 3120, p-value = 1.168e-10
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.08022629 0.14946024
## sample estimates:
## cor
## 0.1149829cor.test(df$prop_dmg_log, df$per_elderly_norm) ##okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_elderly_norm
## t = -8.2802, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1807866 -0.1121330
## sample estimates:
## cor
## -0.1466364cor.test(df$prop_dmg_log, df$per_young_dependent_norm) #okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_young_dependent_norm
## t = 3.7636, df = 3120, p-value = 0.0001706
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.03222182 0.10206555
## sample estimates:
## cor
## 0.06722604cor.test(df$prop_dmg_log, df$per_noenglish_norm)# ##okay remove due to correlation##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_noenglish_norm
## t = 2.6899, df = 3120, p-value = 0.007185
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.01304371 0.08304199
## sample estimates:
## cor
## 0.04810191cor.test(df$prop_dmg_log, df$per_foreign_born_norm)##okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_foreign_born_norm
## t = 7.2815, df = 3120, p-value = 4.159e-13
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.0946150 0.1636045
## sample estimates:
## cor
## 0.1292662cor.test(df$prop_dmg_log, df$per_female_hh_with_kids_under6_norm)## okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_female_hh_with_kids_under6_norm
## t = 5.8064, df = 3120, p-value = 7.025e-09
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.06856248 0.13797377
## sample estimates:
## cor
## 0.103394cor.test(df$prop_dmg_log, df$per_female_hh_with_kids_under18_norm)##okay remove due to correlation##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_female_hh_with_kids_under18_norm
## t = 11.364, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1654444 0.2328194
## sample estimates:
## cor
## 0.1993675cor.test(df$prop_dmg_log, df$per_rural_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_rural_norm
## t = -14.911, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2903661 -0.2248674
## sample estimates:
## cor
## -0.2579131cor.test(df$prop_dmg_log, df$per_per_no_school_completed_norm) ## okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_per_no_school_completed_norm
## t = 2.7448, df = 3120, p-value = 0.006089
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.01402519 0.08401680
## sample estimates:
## cor
## 0.04908125X<-df%>%
select(
per_asian_norm,
per_black_norm,
per_elderly_norm,
per_american_indian_norm,
per_young_dependent_norm,
per_foreign_born_norm,
per_female_hh_with_kids_under6_norm,
per_rural_norm,
per_per_no_school_completed_norm)
ggpairs(X)
social_dmg <- lm(prop_dmg_log~(
per_asian_norm+
per_black_norm+
per_elderly_norm+
per_american_indian_norm+
per_young_dependent_norm+
per_foreign_born_norm+
per_female_hh_with_kids_under6_norm+
per_rural_norm+
per_per_no_school_completed_norm)+
log_pop_2010+numb_haz_log+state+log_median_house_value,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(social_dmg)##
## Call:
## lm(formula = prop_dmg_log ~ (per_asian_norm + per_black_norm +
## per_elderly_norm + per_american_indian_norm + per_young_dependent_norm +
## per_foreign_born_norm + per_female_hh_with_kids_under6_norm +
## per_rural_norm + per_per_no_school_completed_norm) + log_pop_2010 +
## numb_haz_log + state + log_median_house_value, data = df,
## na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -12.0900 -1.1256 -0.0443 1.1216 9.2681
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.489661 2.049253 5.119 3.27e-07 ***
## per_asian_norm -0.155950 0.081291 -1.918 0.055151 .
## per_black_norm 0.165038 0.071876 2.296 0.021734 *
## per_elderly_norm -0.012405 0.063920 -0.194 0.846129
## per_american_indian_norm -0.100713 0.057971 -1.737 0.082434 .
## per_young_dependent_norm -0.113314 0.059921 -1.891 0.058710 .
## per_foreign_born_norm -0.006645 0.073678 -0.090 0.928138
## per_female_hh_with_kids_under6_norm -0.113868 0.068042 -1.674 0.094331 .
## per_rural_norm 0.068825 0.080044 0.860 0.389946
## per_per_no_school_completed_norm -0.132366 0.058825 -2.250 0.024510 *
## log_pop_2010 0.545980 0.061178 8.924 < 2e-16 ***
## numb_haz_log 4.054440 0.097702 41.498 < 2e-16 ***
## stateAL -2.243474 0.684998 -3.275 0.001068 **
## stateAR -2.723213 0.671282 -4.057 5.10e-05 ***
## stateAZ -2.478766 0.838275 -2.957 0.003130 **
## stateCA -1.870360 0.661035 -2.829 0.004693 **
## stateCO -3.057660 0.657095 -4.653 3.41e-06 ***
## stateCT -2.970608 1.012602 -2.934 0.003375 **
## stateDE -4.085775 1.452818 -2.812 0.004950 **
## stateFL -1.828311 0.682125 -2.680 0.007395 **
## stateGA -3.380056 0.642308 -5.262 1.52e-07 ***
## stateIA -3.015463 0.653693 -4.613 4.13e-06 ***
## stateID -1.424453 0.691311 -2.061 0.039434 *
## stateIL -3.511758 0.652734 -5.380 8.01e-08 ***
## stateIN -3.874137 0.657014 -5.897 4.12e-09 ***
## stateKS -3.754701 0.647850 -5.796 7.50e-09 ***
## stateKY -3.096471 0.647971 -4.779 1.85e-06 ***
## stateLA -1.631308 0.685102 -2.381 0.017321 *
## stateMA -2.990505 0.864955 -3.457 0.000553 ***
## stateMD -2.814590 0.765883 -3.675 0.000242 ***
## stateME -2.583511 0.839055 -3.079 0.002095 **
## stateMI -2.259916 0.658580 -3.431 0.000608 ***
## stateMN -2.931052 0.646135 -4.536 5.95e-06 ***
## stateMO -3.604649 0.645000 -5.589 2.49e-08 ***
## stateMS -3.183825 0.685668 -4.643 3.57e-06 ***
## stateMT -3.830943 0.656220 -5.838 5.84e-09 ***
## stateNC -2.320633 0.654786 -3.544 0.000400 ***
## stateND -1.736491 0.674750 -2.574 0.010113 *
## stateNE -1.849594 0.652667 -2.834 0.004629 **
## stateNH -2.301186 0.943663 -2.439 0.014802 *
## stateNJ -1.053263 0.784582 -1.342 0.179549
## stateNM -2.548459 0.708585 -3.597 0.000328 ***
## stateNV -2.221226 0.804065 -2.762 0.005770 **
## stateNY -2.812197 0.676956 -4.154 3.35e-05 ***
## stateOH -2.956402 0.662890 -4.460 8.50e-06 ***
## stateOK -2.946696 0.639636 -4.607 4.26e-06 ***
## stateOR -2.905091 0.706200 -4.114 4.00e-05 ***
## statePA -3.092761 0.681352 -4.539 5.87e-06 ***
## stateRI -3.843613 1.294671 -2.969 0.003013 **
## stateSC -4.096573 0.716886 -5.714 1.21e-08 ***
## stateSD -2.254991 0.641916 -3.513 0.000450 ***
## stateTN -2.877716 0.656150 -4.386 1.19e-05 ***
## stateTX -2.416725 0.633748 -3.813 0.000140 ***
## stateUT -2.241698 0.741389 -3.024 0.002518 **
## stateVA -3.165002 0.634650 -4.987 6.47e-07 ***
## stateVT -1.486150 0.859581 -1.729 0.083924 .
## stateWA -1.921341 0.695851 -2.761 0.005794 **
## stateWI -3.099242 0.658276 -4.708 2.61e-06 ***
## stateWV -2.825021 0.689393 -4.098 4.28e-05 ***
## stateWY -4.088274 0.760205 -5.378 8.10e-08 ***
## log_median_house_value -0.461388 0.173314 -2.662 0.007805 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.276 on 3060 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.5501, Adjusted R-squared: 0.5412
## F-statistic: 62.35 on 60 and 3060 DF, p-value: < 2.2e-16Economic Dimension and damage
cor.test(df$prop_dmg_log, df$per_below_poverty_norm) # no##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_below_poverty_norm
## t = 0.13411, df = 3120, p-value = 0.8933
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.03268204 0.03747797
## sample estimates:
## cor
## 0.002400922cor.test(df$prop_dmg_log, df$median_hh_income_2010_norm)####
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$median_hh_income_2010_norm
## t = 5.1036, df = 3120, p-value = 3.532e-07
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.05608901 0.12566926
## sample estimates:
## cor
## 0.09099018cor.test(df$prop_dmg_log, df$per_rent_norm)# ##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_rent_norm
## t = 4.0743, df = 3120, p-value = 4.73e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.03776475 0.10755430
## sample estimates:
## cor
## 0.07274858cor.test(df$prop_dmg_log, df$per_no_carnorm)# removed bc highly correlated with rent##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_no_carnorm
## t = -2.3376, df = 3120, p-value = 0.01947
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.07677986 -0.00674195
## sample estimates:
## cor
## -0.04181227cor.test(df$prop_dmg_log, df$per_college_or_higher_norm)###
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_college_or_higher_norm
## t = 6.1813, df = 3120, p-value = 7.185e-10
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.07520068 0.14451333
## sample estimates:
## cor
## 0.1099907cor.test(df$prop_dmg_log, df$average_hh_norm)####
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$average_hh_norm
## t = 6.5403, df = 3120, p-value = 7.148e-11
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.08154805 0.15076072
## sample estimates:
## cor
## 0.1162956cor.test(df$prop_dmg_log, df$per_lack_plumbing_norm)## no##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_lack_plumbing_norm
## t = -0.95465, df = 3120, p-value = 0.3398
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.05213744 0.01800251
## sample estimates:
## cor
## -0.01708849cor.test(df$prop_dmg_log, df$per_lack_kitchen_norm) ###
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_lack_kitchen_norm
## t = -10.108, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2118239 -0.1438855
## sample estimates:
## cor
## -0.1780669cor.test(df$prop_dmg_log, df$per_mobile_home_norm)#no##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_mobile_home_norm
## t = -1.8258, df = 3120, p-value = 0.06797
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.067672720 0.002412903
## sample estimates:
## cor
## -0.03267007cor.test(df$prop_dmg_log, df$per_unemployed_norm)## ##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_unemployed_norm
## t = 6.3885, df = 3120, p-value = 1.925e-10
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.0788651 0.1481207
## sample estimates:
## cor
## 0.1136309X<-df%>%
select(median_hh_income_2010_norm,
per_rent_norm,
average_hh_norm,
per_college_or_higher_norm,
per_lack_kitchen_norm,
per_unemployed_norm)
ggpairs(X)
econ_dmg <- lm(prop_dmg_log~(median_hh_income_2010_norm+
per_rent_norm+
average_hh_norm+
per_college_or_higher_norm+
per_lack_kitchen_norm+
per_unemployed_norm)+
log_pop_2010+numb_haz_log+state+log_median_house_value,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(econ_dmg)##
## Call:
## lm(formula = prop_dmg_log ~ (median_hh_income_2010_norm + per_rent_norm +
## average_hh_norm + per_college_or_higher_norm + per_lack_kitchen_norm +
## per_unemployed_norm) + log_pop_2010 + numb_haz_log + state +
## log_median_house_value, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -12.1033 -1.1040 -0.0606 1.1528 9.3162
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8.67010 2.62919 3.298 0.000986 ***
## median_hh_income_2010_norm 0.04630 0.10015 0.462 0.643913
## per_rent_norm -0.14213 0.05862 -2.425 0.015386 *
## average_hh_norm -0.18974 0.06303 -3.010 0.002630 **
## per_college_or_higher_norm -0.10285 0.08517 -1.208 0.227302
## per_lack_kitchen_norm -0.06753 0.05844 -1.156 0.247953
## per_unemployed_norm -0.01984 0.06101 -0.325 0.745014
## log_pop_2010 0.48937 0.05031 9.726 < 2e-16 ***
## numb_haz_log 4.07817 0.09743 41.857 < 2e-16 ***
## stateAL -1.58750 0.69258 -2.292 0.021964 *
## stateAR -2.20431 0.68242 -3.230 0.001250 **
## stateAZ -2.20430 0.85237 -2.586 0.009753 **
## stateCA -1.69975 0.67456 -2.520 0.011794 *
## stateCO -2.68122 0.68175 -3.933 8.58e-05 ***
## stateCT -2.54037 1.01238 -2.509 0.012149 *
## stateDE -3.70183 1.45946 -2.536 0.011248 *
## stateFL -1.42087 0.69495 -2.045 0.040984 *
## stateGA -2.73592 0.65068 -4.205 2.69e-05 ***
## stateIA -2.75328 0.68335 -4.029 5.74e-05 ***
## stateID -1.04792 0.72423 -1.447 0.148018
## stateIL -3.15709 0.67533 -4.675 3.07e-06 ***
## stateIN -3.46607 0.67334 -5.148 2.81e-07 ***
## stateKS -3.34231 0.67585 -4.945 8.01e-07 ***
## stateKY -2.68486 0.66487 -4.038 5.52e-05 ***
## stateLA -1.01788 0.68847 -1.478 0.139388
## stateMA -2.63882 0.86487 -3.051 0.002299 **
## stateMD -2.33793 0.76400 -3.060 0.002232 **
## stateME -2.15469 0.85035 -2.534 0.011330 *
## stateMI -1.90687 0.68828 -2.771 0.005631 **
## stateMN -2.75374 0.67726 -4.066 4.90e-05 ***
## stateMO -3.19050 0.66482 -4.799 1.67e-06 ***
## stateMS -2.36200 0.69228 -3.412 0.000653 ***
## stateMT -3.44940 0.68927 -5.004 5.92e-07 ***
## stateNC -1.76402 0.67100 -2.629 0.008608 **
## stateND -1.42553 0.72143 -1.976 0.048246 *
## stateNE -1.41973 0.68230 -2.081 0.037535 *
## stateNH -1.84218 0.95476 -1.929 0.053764 .
## stateNJ -0.67811 0.78076 -0.869 0.385172
## stateNM -2.39639 0.73757 -3.249 0.001171 **
## stateNV -2.02413 0.81510 -2.483 0.013070 *
## stateNY -2.33718 0.68782 -3.398 0.000688 ***
## stateOH -2.51343 0.67244 -3.738 0.000189 ***
## stateOK -2.63630 0.68379 -3.855 0.000118 ***
## stateOR -2.53443 0.72449 -3.498 0.000475 ***
## statePA -2.60923 0.68818 -3.791 0.000153 ***
## stateRI -3.49250 1.29587 -2.695 0.007075 **
## stateSC -3.34704 0.71740 -4.665 3.21e-06 ***
## stateSD -1.98080 0.70030 -2.829 0.004707 **
## stateTN -2.42557 0.67460 -3.596 0.000329 ***
## stateTX -1.97323 0.64060 -3.080 0.002086 **
## stateUT -1.73860 0.77180 -2.253 0.024352 *
## stateVA -2.67632 0.64241 -4.166 3.19e-05 ***
## stateVT -1.07010 0.88115 -1.214 0.224675
## stateWA -1.69522 0.72297 -2.345 0.019101 *
## stateWI -2.79027 0.68191 -4.092 4.39e-05 ***
## stateWV -2.41664 0.70810 -3.413 0.000651 ***
## stateWY -3.80937 0.77555 -4.912 9.50e-07 ***
## log_median_house_value -0.29487 0.21710 -1.358 0.174491
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.28 on 3063 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.5479, Adjusted R-squared: 0.5395
## F-statistic: 65.13 on 57 and 3063 DF, p-value: < 2.2e-16Health Dimension and damage
cor.test(df$prop_dmg_log, df$life_expectancy_2010_norm) # highly correlated##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$life_expectancy_2010_norm
## t = -2.2964, df = 3120, p-value = 0.02172
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.076048243 -0.006006069
## sample estimates:
## cor
## -0.04107762cor.test(df$prop_dmg_log, df$per_hypertension_2009_norm)# highly correlated##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_hypertension_2009_norm
## t = 3.7473, df = 3120, p-value = 0.000182
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.03193164 0.10177809
## sample estimates:
## cor
## 0.06693687cor.test(df$prop_dmg_log, df$per_heart_disease_35_65_norm)# highly correlated##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_heart_disease_35_65_norm
## t = 2.9439, df = 3120, p-value = 0.003265
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.01758337 0.08754968
## sample estimates:
## cor
## 0.05263111cor.test(df$prop_dmg_log, df$per_heart_disease_65_more_norm)# ##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_heart_disease_65_more_norm
## t = 2.729, df = 3120, p-value = 0.006388
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.01374206 0.08373560
## sample estimates:
## cor
## 0.04879874cor.test(df$prop_dmg_log, df$per_stroke_35_65_norm) # ##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_stroke_35_65_norm
## t = 6.5168, df = 3120, p-value = 8.344e-11
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.08113299 0.15035237
## sample estimates:
## cor
## 0.1158834cor.test(df$prop_dmg_log, df$per_stroke_65_more_norm) #no##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_stroke_65_more_norm
## t = 0.43374, df = 3120, p-value = 0.6645
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.02732260 0.04283359
## sample estimates:
## cor
## 0.007765046cor.test(df$prop_dmg_log, df$per_diabetes_2010_norm)# ##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_diabetes_2010_norm
## t = 4.6924, df = 3120, p-value = 2.816e-06
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.04877624 0.11844558
## sample estimates:
## cor
## 0.08371321cor.test(df$prop_dmg_log, df$per_disability_norm)# no##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_disability_norm
## t = 0.015924, df = 3120, p-value = 0.9873
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.03479548 0.03536493
## sample estimates:
## cor
## 0.0002850765cor.test(df$prop_dmg_log, df$per_nursingnorm)# okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_nursingnorm
## t = -5.4141, df = 3120, p-value = 6.627e-08
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.13111181 -0.06160362
## sample estimates:
## cor
## -0.09647533X<-df%>%
select(
per_diabetes_2010_norm,
per_nursingnorm)
ggpairs(X)
health_dmg <- lm(prop_dmg_log~(per_diabetes_2010_norm+
per_nursingnorm)+
log_pop_2010+numb_haz_log+state+log_median_house_value,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(health_dmg)##
## Call:
## lm(formula = prop_dmg_log ~ (per_diabetes_2010_norm + per_nursingnorm) +
## log_pop_2010 + numb_haz_log + state + log_median_house_value,
## data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -11.9869 -1.1317 -0.0787 1.1672 9.6285
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.82750 1.93101 5.607 2.24e-08 ***
## per_diabetes_2010_norm -0.15927 0.07622 -2.090 0.036740 *
## per_nursingnorm 0.05581 0.04802 1.162 0.245212
## log_pop_2010 0.43095 0.04530 9.513 < 2e-16 ***
## numb_haz_log 4.09653 0.09750 42.016 < 2e-16 ***
## stateAL -0.60635 0.60840 -0.997 0.319026
## stateAR -1.43887 0.60017 -2.397 0.016570 *
## stateAZ -1.45088 0.79257 -1.831 0.067257 .
## stateCA -1.01336 0.60979 -1.662 0.096650 .
## stateCO -1.99921 0.58888 -3.395 0.000695 ***
## stateCT -1.60035 0.96639 -1.656 0.097821 .
## stateDE -2.61791 1.42312 -1.840 0.065930 .
## stateFL -0.34718 0.59839 -0.580 0.561836
## stateGA -1.89444 0.56356 -3.362 0.000785 ***
## stateIA -1.99757 0.58118 -3.437 0.000596 ***
## stateID -0.42741 0.62221 -0.687 0.492187
## stateIL -2.31048 0.57605 -4.011 6.19e-05 ***
## stateIN -2.60898 0.57944 -4.503 6.96e-06 ***
## stateKS -2.73264 0.57693 -4.736 2.27e-06 ***
## stateKY -1.81461 0.57168 -3.174 0.001518 **
## stateLA -0.10812 0.60867 -0.178 0.859024
## stateMA -1.78175 0.81046 -2.198 0.027992 *
## stateMD -1.34327 0.70617 -1.902 0.057240 .
## stateME -1.22443 0.77414 -1.582 0.113828
## stateMI -0.93983 0.58209 -1.615 0.106504
## stateMN -1.94786 0.57835 -3.368 0.000767 ***
## stateMO -2.40478 0.56970 -4.221 2.50e-05 ***
## stateMS -1.49731 0.60332 -2.482 0.013125 *
## stateMT -2.81570 0.60153 -4.681 2.98e-06 ***
## stateNC -0.82436 0.57791 -1.426 0.153839
## stateND -0.74268 0.61864 -1.201 0.230036
## stateNE -0.86915 0.58363 -1.489 0.136534
## stateNH -0.94506 0.89124 -1.060 0.289051
## stateNJ 0.18162 0.73285 0.248 0.804288
## stateNM -1.59764 0.65724 -2.431 0.015122 *
## stateNV -1.22488 0.75568 -1.621 0.105143
## stateNY -1.51031 0.60270 -2.506 0.012265 *
## stateOH -1.60997 0.58633 -2.746 0.006071 **
## stateOK -1.88018 0.59361 -3.167 0.001553 **
## stateOR -1.76388 0.64101 -2.752 0.005963 **
## statePA -1.66527 0.59875 -2.781 0.005448 **
## stateRI -2.68570 1.25817 -2.135 0.032872 *
## stateSC -2.38803 0.63633 -3.753 0.000178 ***
## stateSD -1.43097 0.59696 -2.397 0.016584 *
## stateTN -1.50662 0.58076 -2.594 0.009526 **
## stateTX -1.31138 0.55205 -2.375 0.017587 *
## stateUT -1.32330 0.66866 -1.979 0.047902 *
## stateVA -1.72924 0.56011 -3.087 0.002038 **
## stateVT -0.27610 0.80133 -0.345 0.730454
## stateWA -0.89779 0.63819 -1.407 0.159594
## stateWI -1.92961 0.58852 -3.279 0.001054 **
## stateWV -1.44001 0.61587 -2.338 0.019441 *
## stateWY -3.05843 0.70111 -4.362 1.33e-05 ***
## log_median_house_value -0.49882 0.17427 -2.862 0.004234 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.285 on 3067 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.5453, Adjusted R-squared: 0.5375
## F-statistic: 69.41 on 53 and 3067 DF, p-value: < 2.2e-16Institutional Dimension and damage
cor.test(df$prop_dmg_log, df$FEMA_total_norm) # okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$FEMA_total_norm
## t = 3.9876, df = 3120, p-value = 6.827e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.03621916 0.10602425
## sample estimates:
## cor
## 0.07120889cor.test(df$prop_dmg_log, df$number_research_institutions_norm) # okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$number_research_institutions_norm
## t = 8.0537, df = 3120, p-value = 1.132e-15
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1081695 0.1769028
## sample estimates:
## cor
## 0.1427082cor.test(df$prop_dmg_log, df$employees_2010_norm) # okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$employees_2010_norm
## t = 11.898, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1745366 0.2416552
## sample estimates:
## cor
## 0.2083412X<-df%>%
select(
FEMA_total_norm,
number_research_institutions_norm,
employees_2010_norm)
ggpairs(X)
inst_dmg <- lm(prop_dmg_log~(FEMA_total_norm+
number_research_institutions_norm+
employees_2010_norm)+
log_pop_2010+numb_haz_log+state+log_median_house_value,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(inst_dmg)##
## Call:
## lm(formula = prop_dmg_log ~ (FEMA_total_norm + number_research_institutions_norm +
## employees_2010_norm) + log_pop_2010 + numb_haz_log + state +
## log_median_house_value, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -11.9665 -1.1185 -0.0688 1.1478 9.6016
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8.782201 1.645493 5.337 1.01e-07 ***
## FEMA_total_norm 0.003421 0.045747 0.075 0.940394
## number_research_institutions_norm 0.012054 0.055881 0.216 0.829224
## employees_2010_norm 0.018667 0.060923 0.306 0.759324
## log_pop_2010 0.382230 0.047584 8.033 1.35e-15 ***
## numb_haz_log 4.113760 0.097409 42.232 < 2e-16 ***
## stateAL -0.674164 0.599096 -1.125 0.260549
## stateAR -1.377543 0.595084 -2.315 0.020686 *
## stateAZ -1.473426 0.792433 -1.859 0.063071 .
## stateCA -1.113159 0.607310 -1.833 0.066909 .
## stateCO -1.893169 0.588094 -3.219 0.001299 **
## stateCT -1.546376 0.965386 -1.602 0.109298
## stateDE -2.653506 1.422544 -1.865 0.062231 .
## stateFL -0.411691 0.595694 -0.691 0.489548
## stateGA -2.008553 0.554338 -3.623 0.000296 ***
## stateIA -1.765867 0.573952 -3.077 0.002112 **
## stateID -0.364015 0.621410 -0.586 0.558060
## stateIL -2.160469 0.572098 -3.776 0.000162 ***
## stateIN -2.505496 0.575584 -4.353 1.39e-05 ***
## stateKS -2.521351 0.569834 -4.425 9.99e-06 ***
## stateKY -1.809775 0.566516 -3.195 0.001415 **
## stateLA -0.200771 0.604815 -0.332 0.739947
## stateMA -1.791807 0.809815 -2.213 0.026998 *
## stateMD -1.412833 0.699882 -2.019 0.043608 *
## stateME -1.080403 0.773389 -1.397 0.162523
## stateMI -0.833616 0.580580 -1.436 0.151152
## stateMN -1.726749 0.572223 -3.018 0.002569 **
## stateMO -2.289181 0.564406 -4.056 5.12e-05 ***
## stateMS -1.634025 0.591282 -2.764 0.005752 **
## stateMT -2.646800 0.598457 -4.423 1.01e-05 ***
## stateNC -0.851038 0.571981 -1.488 0.136886
## stateND -0.518472 0.612756 -0.846 0.397545
## stateNE -0.595364 0.573572 -1.038 0.299356
## stateNH -0.827172 0.890557 -0.929 0.353053
## stateNJ 0.156077 0.727101 0.215 0.830049
## stateNM -1.621433 0.656740 -2.469 0.013607 *
## stateNV -1.184761 0.756190 -1.567 0.117276
## stateNY -1.429924 0.602299 -2.374 0.017653 *
## stateOH -1.538139 0.580129 -2.651 0.008058 **
## stateOK -1.822283 0.591076 -3.083 0.002068 **
## stateOR -1.710757 0.640477 -2.671 0.007601 **
## statePA -1.547626 0.597129 -2.592 0.009593 **
## stateRI -2.612200 1.259477 -2.074 0.038159 *
## stateSC -2.485473 0.629184 -3.950 7.98e-05 ***
## stateSD -1.255794 0.593644 -2.115 0.034477 *
## stateTN -1.491170 0.574691 -2.595 0.009511 **
## stateTX -1.286253 0.548193 -2.346 0.019022 *
## stateUT -1.248906 0.668751 -1.868 0.061924 .
## stateVA -1.820644 0.551790 -3.300 0.000980 ***
## stateVT -0.136167 0.801151 -0.170 0.865050
## stateWA -0.858134 0.636594 -1.348 0.177756
## stateWI -1.763141 0.585391 -3.012 0.002617 **
## stateWV -1.395697 0.611057 -2.284 0.022436 *
## stateWY -2.931114 0.700297 -4.186 2.93e-05 ***
## log_median_house_value -0.287235 0.143889 -1.996 0.045997 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.288 on 3066 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.5444, Adjusted R-squared: 0.5364
## F-statistic: 67.84 on 54 and 3066 DF, p-value: < 2.2e-16Environmental Dimension and damage
df$air_quality_norm <- z_score(df$air_quality)
df$water_quality_norm <- z_score(df$water_quality)
df$built_quality_norm <- z_score(df$built_quality)
df$land_quality_norm <- z_score(df$land_quality)
cor.test(df$prop_dmg_log, df$air_quality_norm)#okay ##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$air_quality_norm
## t = 6.8604, df = 3120, p-value = 8.246e-12
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.08719789 0.15631692
## sample estimates:
## cor
## 0.1219052cor.test(df$prop_dmg_log, df$water_quality_norm)# no##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$water_quality_norm
## t = 1.6693, df = 3120, p-value = 0.09516
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.005214242 0.064883646
## sample estimates:
## cor
## 0.02987143cor.test(df$prop_dmg_log, df$built_quality_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$built_quality_norm
## t = 9.0977, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1263896 0.1947390
## sample estimates:
## cor
## 0.160757cor.test(df$prop_dmg_log, df$land_quality_norm)###
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$land_quality_norm
## t = 2.3181, df = 3120, p-value = 0.02051
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.006394862 0.076434792
## sample estimates:
## cor
## 0.04146577cor.test(df$prop_dmg_log, df$impervious_surface_norm)#okay##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$impervious_surface_norm
## t = 7.9858, df = 3120, p-value = 1.945e-15
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1069805 0.1757373
## sample estimates:
## cor
## 0.1415296X<-df%>%
select(air_quality_norm,
built_quality_norm,
land_quality_norm,
impervious_surface_norm)
ggpairs(X)
env_dmg <- lm(prop_dmg_log~(air_quality_norm+
built_quality_norm+
land_quality_norm+
impervious_surface_norm)+
log_pop_2010+numb_haz_log+state+log_median_house_value,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(env_dmg)##
## Call:
## lm(formula = prop_dmg_log ~ (air_quality_norm + built_quality_norm +
## land_quality_norm + impervious_surface_norm) + log_pop_2010 +
## numb_haz_log + state + log_median_house_value, data = df,
## na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -12.0305 -1.1435 -0.0797 1.1525 9.6132
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8.0876497 1.6793371 4.816 1.54e-06 ***
## air_quality_norm -0.0005011 0.0624259 -0.008 0.993596
## built_quality_norm 0.0553946 0.0520755 1.064 0.287532
## land_quality_norm 0.0143429 0.0577933 0.248 0.804015
## impervious_surface_norm -0.1014320 0.0575833 -1.761 0.078256 .
## log_pop_2010 0.4192817 0.0502310 8.347 < 2e-16 ***
## numb_haz_log 4.1023444 0.0976251 42.021 < 2e-16 ***
## stateAL -0.8271502 0.6482978 -1.276 0.202095
## stateAR -1.4791512 0.6413128 -2.306 0.021152 *
## stateAZ -1.6493718 0.8084579 -2.040 0.041421 *
## stateCA -1.2266014 0.6497832 -1.888 0.059159 .
## stateCO -1.9344103 0.6198406 -3.121 0.001820 **
## stateCT -1.6363792 1.0014200 -1.634 0.102349
## stateDE -2.7717869 1.4574922 -1.902 0.057297 .
## stateFL -0.5179052 0.6353437 -0.815 0.415045
## stateGA -2.1238349 0.6102874 -3.480 0.000508 ***
## stateIA -1.8252193 0.6432227 -2.838 0.004575 **
## stateID -0.4462891 0.6606119 -0.676 0.499365
## stateIL -2.2502347 0.6447842 -3.490 0.000490 ***
## stateIN -2.6274175 0.6522134 -4.028 5.75e-05 ***
## stateKS -2.5389159 0.6276650 -4.045 5.36e-05 ***
## stateKY -1.9288776 0.6225209 -3.098 0.001963 **
## stateLA -0.3074064 0.6543928 -0.470 0.638561
## stateMA -1.7262244 0.8588887 -2.010 0.044536 *
## stateMD -1.5365786 0.7656108 -2.007 0.044838 *
## stateME -1.1992550 0.7983809 -1.502 0.133172
## stateMI -0.9160989 0.6348986 -1.443 0.149149
## stateMN -1.8133690 0.6337741 -2.861 0.004249 **
## stateMO -2.3807861 0.6162853 -3.863 0.000114 ***
## stateMS -1.7541654 0.6441861 -2.723 0.006504 **
## stateMT -2.6833412 0.6302526 -4.258 2.13e-05 ***
## stateNC -0.9843947 0.6285477 -1.566 0.117419
## stateND -0.5252597 0.6672732 -0.787 0.431241
## stateNE -0.6048033 0.6321800 -0.957 0.338797
## stateNH -0.9562233 0.9149765 -1.045 0.296069
## stateNJ 0.1810045 0.8009067 0.226 0.821217
## stateNM -1.7136819 0.6715604 -2.552 0.010765 *
## stateNV -1.2726560 0.7678700 -1.657 0.097544 .
## stateNY -1.4861345 0.6643551 -2.237 0.025361 *
## stateOH -1.6639246 0.6579025 -2.529 0.011484 *
## stateOK -1.9117156 0.6329688 -3.020 0.002547 **
## stateOR -1.7952636 0.6823820 -2.631 0.008559 **
## statePA -1.6671200 0.6570319 -2.537 0.011219 *
## stateRI -2.5402802 1.3010841 -1.952 0.050978 .
## stateSC -2.6268602 0.6772533 -3.879 0.000107 ***
## stateSD -1.2758750 0.6436566 -1.982 0.047543 *
## stateTN -1.6231278 0.6307898 -2.573 0.010124 *
## stateTX -1.3720426 0.5939512 -2.310 0.020953 *
## stateUT -1.3415005 0.6905623 -1.943 0.052153 .
## stateVA -1.8303909 0.6121452 -2.990 0.002811 **
## stateVT -0.2316488 0.8309745 -0.279 0.780442
## stateWA -0.9853443 0.6757190 -1.458 0.144883
## stateWI -1.8779134 0.6454518 -2.909 0.003647 **
## stateWV -1.5291596 0.6610360 -2.313 0.020773 *
## stateWY -2.9856004 0.7220863 -4.135 3.65e-05 ***
## log_median_house_value -0.2513098 0.1452408 -1.730 0.083678 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.286 on 3065 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.5453, Adjusted R-squared: 0.5371
## F-statistic: 66.83 on 55 and 3065 DF, p-value: < 2.2e-16Vulnerability using Dmg
X<-df%>%
select(
per_asian_norm,
per_black_norm,
per_elderly_norm,
per_american_indian_norm,
per_young_dependent_norm,
per_foreign_born_norm,
per_female_hh_with_kids_under6_norm,
per_rural_norm,
per_per_no_school_completed_norm,
median_hh_income_2010_norm,
per_rent_norm,
average_hh_norm,
per_college_or_higher_norm,
per_lack_kitchen_norm,
per_unemployed_norm,
per_diabetes_2010_norm,
per_nursingnorm,
FEMA_total_norm,
number_research_institutions_norm,
employees_2010_norm,
air_quality_norm,
built_quality_norm,
land_quality_norm,
impervious_surface_norm
)
ggpairs(X)
model_dmg <- lm(prop_dmg_log~
(per_asian_norm +
per_black_norm + per_elderly_norm + per_american_indian_norm +
per_young_dependent_norm + per_foreign_born_norm + per_female_hh_with_kids_under6_norm +
per_rural_norm + per_per_no_school_completed_norm)+
(median_hh_income_2010_norm+
per_rent_norm+
average_hh_norm+
per_college_or_higher_norm+
per_lack_kitchen_norm+
per_unemployed_norm)+
(per_diabetes_2010_norm+
per_nursingnorm)+
(FEMA_total_norm+
number_research_institutions_norm+
employees_2010_norm)+
(air_quality_norm+
built_quality_norm+
land_quality_norm+
impervious_surface_norm)+
log_pop_2010+numb_haz_log+state+log_median_house_value
,data=df, na.rm=TRUE)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregardedsummary(model_dmg)##
## Call:
## lm(formula = prop_dmg_log ~ (per_asian_norm + per_black_norm +
## per_elderly_norm + per_american_indian_norm + per_young_dependent_norm +
## per_foreign_born_norm + per_female_hh_with_kids_under6_norm +
## per_rural_norm + per_per_no_school_completed_norm) + (median_hh_income_2010_norm +
## per_rent_norm + average_hh_norm + per_college_or_higher_norm +
## per_lack_kitchen_norm + per_unemployed_norm) + (per_diabetes_2010_norm +
## per_nursingnorm) + (FEMA_total_norm + number_research_institutions_norm +
## employees_2010_norm) + (air_quality_norm + built_quality_norm +
## land_quality_norm + impervious_surface_norm) + log_pop_2010 +
## numb_haz_log + state + log_median_house_value, data = df,
## na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -12.040 -1.136 -0.069 1.141 9.273
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.736026 2.830725 3.793 0.000152 ***
## per_asian_norm -0.145703 0.088715 -1.642 0.100616
## per_black_norm 0.250827 0.093837 2.673 0.007558 **
## per_elderly_norm -0.048092 0.089920 -0.535 0.592802
## per_american_indian_norm -0.016554 0.071608 -0.231 0.817197
## per_young_dependent_norm -0.101082 0.072448 -1.395 0.163047
## per_foreign_born_norm 0.050701 0.082958 0.611 0.541134
## per_female_hh_with_kids_under6_norm -0.067535 0.089810 -0.752 0.452121
## per_rural_norm -0.029672 0.091606 -0.324 0.746024
## per_per_no_school_completed_norm -0.108975 0.062508 -1.743 0.081367 .
## median_hh_income_2010_norm -0.028317 0.120276 -0.235 0.813886
## per_rent_norm -0.053046 0.090533 -0.586 0.557968
## average_hh_norm -0.124471 0.116687 -1.067 0.286186
## per_college_or_higher_norm -0.062472 0.094449 -0.661 0.508380
## per_lack_kitchen_norm -0.073335 0.062537 -1.173 0.241025
## per_unemployed_norm -0.027950 0.067595 -0.413 0.679275
## per_diabetes_2010_norm -0.117060 0.134977 -0.867 0.385867
## per_nursingnorm 0.078365 0.053370 1.468 0.142114
## FEMA_total_norm 0.014194 0.046215 0.307 0.758771
## number_research_institutions_norm 0.022741 0.060545 0.376 0.707243
## employees_2010_norm 0.054859 0.066452 0.826 0.409130
## air_quality_norm 0.006442 0.062474 0.103 0.917881
## built_quality_norm 0.132875 0.069915 1.901 0.057458 .
## land_quality_norm 0.012206 0.063609 0.192 0.847838
## impervious_surface_norm -0.096894 0.070300 -1.378 0.168213
## log_pop_2010 0.488611 0.074653 6.545 6.95e-11 ***
## numb_haz_log 4.047829 0.098352 41.157 < 2e-16 ***
## stateAL -2.512743 0.852361 -2.948 0.003223 **
## stateAR -2.956583 0.817414 -3.617 0.000303 ***
## stateAZ -2.772147 0.924182 -3.000 0.002726 **
## stateCA -2.101026 0.782949 -2.683 0.007325 **
## stateCO -3.234512 0.773977 -4.179 3.01e-05 ***
## stateCT -3.153110 1.118044 -2.820 0.004830 **
## stateDE -4.345514 1.543795 -2.815 0.004912 **
## stateFL -2.055335 0.835452 -2.460 0.013943 *
## stateGA -3.612730 0.811839 -4.450 8.89e-06 ***
## stateIA -3.284601 0.815143 -4.029 5.73e-05 ***
## stateID -1.569912 0.822792 -1.908 0.056481 .
## stateIL -3.799993 0.826527 -4.598 4.45e-06 ***
## stateIN -4.076426 0.837453 -4.868 1.19e-06 ***
## stateKS -3.925624 0.801713 -4.897 1.03e-06 ***
## stateKY -3.265712 0.832036 -3.925 8.87e-05 ***
## stateLA -1.881808 0.842469 -2.234 0.025576 *
## stateMA -3.106096 1.000743 -3.104 0.001928 **
## stateMD -3.044350 0.921394 -3.304 0.000964 ***
## stateME -2.711926 0.944226 -2.872 0.004106 **
## stateMI -2.414794 0.820610 -2.943 0.003278 **
## stateMN -3.257180 0.794031 -4.102 4.20e-05 ***
## stateMO -3.809988 0.804174 -4.738 2.26e-06 ***
## stateMS -3.404965 0.861459 -3.953 7.91e-05 ***
## stateMT -4.058219 0.773988 -5.243 1.69e-07 ***
## stateNC -2.582407 0.821402 -3.144 0.001683 **
## stateND -1.969912 0.832320 -2.367 0.018006 *
## stateNE -2.082812 0.799174 -2.606 0.009200 **
## stateNH -2.479454 1.046185 -2.370 0.017850 *
## stateNJ -1.144062 0.937620 -1.220 0.222492
## stateNM -2.751933 0.830178 -3.315 0.000928 ***
## stateNV -2.545736 0.877685 -2.901 0.003752 **
## stateNY -3.003765 0.833433 -3.604 0.000318 ***
## stateOH -3.161208 0.851813 -3.711 0.000210 ***
## stateOK -3.172936 0.800229 -3.965 7.51e-05 ***
## stateOR -3.052699 0.829036 -3.682 0.000235 ***
## statePA -3.261015 0.834428 -3.908 9.51e-05 ***
## stateRI -3.976602 1.404080 -2.832 0.004654 **
## stateSC -4.339054 0.869987 -4.987 6.46e-07 ***
## stateSD -2.463970 0.797840 -3.088 0.002031 **
## stateTN -3.084062 0.832223 -3.706 0.000214 ***
## stateTX -2.566472 0.787931 -3.257 0.001137 **
## stateUT -2.286320 0.858621 -2.663 0.007791 **
## stateVA -3.347902 0.817524 -4.095 4.33e-05 ***
## stateVT -1.646035 0.971395 -1.695 0.090271 .
## stateWA -2.194724 0.823547 -2.665 0.007740 **
## stateWI -3.379769 0.805679 -4.195 2.81e-05 ***
## stateWV -3.075683 0.863986 -3.560 0.000377 ***
## stateWY -4.298130 0.850040 -5.056 4.53e-07 ***
## log_median_house_value -0.413063 0.242152 -1.706 0.088147 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.276 on 3045 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.5521, Adjusted R-squared: 0.5411
## F-statistic: 50.05 on 75 and 3045 DF, p-value: < 2.2e-16
Social Dimension and Causality